Tzohar/PassLLM

World's most accurate password guessing AI tool. A PyTorch implementation of PassLLM (USENIX 2025) that leverages PII and LoRA fine-tuning to outperform existing tools by over 45% on consumer hardware.

47
/ 100
Emerging

This project helps security professionals and penetration testers generate highly accurate password guesses for a specific target. By inputting personal details like names, birthdays, emails, and even previous passwords, it produces a ranked list of the most probable passwords. This tool is designed for security auditors, forensic investigators, or anyone needing to test the strength of passwords based on publicly available or leaked PII.

Use this if you need to perform targeted password guessing with significantly higher accuracy than existing tools, leveraging personal information to predict user passwords.

Not ideal if you need a general-purpose password cracker that doesn't rely on specific personal data for a particular target.

penetration-testing digital-forensics security-auditing password-recovery cybersecurity-research
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 13 / 25
Community 15 / 25

How are scores calculated?

Stars

85

Forks

12

Language

Python

License

GPL-3.0

Last pushed

Mar 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Tzohar/PassLLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.